correlation-regime

Correlation-regime detection and crisis attribution — edge-density regime states with hysteresis, causal (no look-ahead) smoothing, regime-aware exposure context, first-mover crisis attribution with honest NAME / MACRO / AMBIGUOUS / ABSTAIN verdicts, and a correlation-rewiring leaderboard that catches slow bleed-outs

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./agent/src/skills/correlation-regime/SKILL.md

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable code and clear, validated workflows, and is well-structured for navigation; its main weakness is verbosity from repeated cautions and the lack of a worked end-to-end example.

Suggestions

De-duplicate the 'not a trade signal' caution — state it once prominently in the Overview and reference it from Mode 2/Output/Notes rather than re-explaining it four times.

Add one short end-to-end example (sample returns in -> calls to compute_edge_density, detect_regimes, first_mover_attribution -> expected output) so users can run the full pipeline without assembling it themselves.

Consider moving the four long Python functions into a bundled scripts/ file referenced from each mode, shortening SKILL.md to an overview with inline key snippets.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and assumes competence (no basic-concept padding), but it is long and repeats the same caution multiple times — the 'not a trade signal' point is made in Overview, Mode 2, Output Format, and Notes.	3 / 5
Actionability	Four complete, executable, docstringed Python functions plus a threshold-selection table and an output template; the minor gap is the absence of a worked end-to-end example wiring the modes together with sample data.	4 / 5
Workflow Clarity	Each mode has a clearly numbered workflow with explicit validation disciplines (causal smoothing re-check, walk-forward calibration, baseline-from-detected-calm); checkpoints are mostly present, though there are no classic validate-fix-retry loops.	4 / 5
Progressive Disclosure	Well-organized into Overview/Modes 1-4/Dependencies/Output/Notes/References with clearly signaled one-level-deep external references (GitHub repo, Maven artifacts); the single-file monolithic form is acceptable since no bundle files are provided.	4 / 5
	Total	15 / 20 Passed

Description

58%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is specific and carves a distinctive niche, but it is missing an explicit 'when to use' trigger clause and leans on technical jargon over natural user phrasing, capping completeness and trigger-term quality.

Suggestions

Add an explicit 'Use when…' clause naming the temporal questions the skill answers (e.g. 'Use when monitoring correlation regime shifts, sizing exposure during fused regimes, or attributing who moved first in a crisis').

Soften the jargon with one or two natural trigger phrases a user would actually say (e.g. 'market correlation', 'who broke first', 'crisis blame') to broaden trigger-term coverage.

Briefly contrast the trigger against the sibling correlation-analysis skill in the description so users pick the temporal/attribution skill over the snapshot one.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several concrete actions/outputs — 'edge-density regime states with hysteresis', 'causal (no look-ahead) smoothing', 'first-mover crisis attribution', 'correlation-rewiring leaderboard' — covering all four modes with only minor gaps.	4 / 5
Completeness	The 'what' is clear and comprehensive, but there is no 'Use when…' clause or equivalent explicit trigger guidance, which per the rubric caps completeness at 3.	3 / 5
Trigger Term Quality	Relevant domain keywords (correlation, regime, crisis, attribution) are present but technical; common user-facing variations or synonyms a non-specialist would say are missing.	3 / 5
Distinctiveness Conflict Risk	Clear niche (regime detection + crisis attribution with NAME/MACRO/AMBIGUOUS/ABSTAIN verdicts) with minimal conflict risk, though minor overlap with the related correlation-analysis and volatility skills.	4 / 5
	Total	14 / 20 Passed

Validation

87%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (505 lines); consider splitting into references/ and linking	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: HKUDS/Vibe-Trading
Path: agent/src/skills/correlation-regime/SKILL.md
Commit: 99e84ab

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.